When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model

• URL: http://arxiv.org/abs/2606.21641v2
• Date: Fri, 26 Jun 2026 10:02:21 GMT
• Title: When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
• Abstract summary: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge.<n>We test that claim under a budget-matched, multi-seed protocol on eight PMLB benchmarks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations. We test that claim under a budget-matched, multi-seed protocol on eight PMLB tabular benchmarks, comparing an LLM advisor (LLM-OptFlow) against four classical baselines (random search, Optuna-TPE, Gaussian-process Bayesian optimization, and successive halving) over one shared search space, with paired tests and bootstrap 95% CIs across 8 x 5 = 40 (task, seed) units. The finding is cautionary. The advisor's strong first point is not an LLM output at all: like prior LLM-HPO systems the loop is seeded with a fixed default configuration, evaluated before any model call, which alone reaches 88.7% mean best-CV, identical to within 0.01 pp across all seven advisor models tested. The LLM's own proposals add only +0.40 pp of cross-validation accuracy over that seed and nothing on held-out test (LLM-Default = -0.01 pp, p = 0.92). When the same seed is granted to classical search, the apparent lead collapses: against seeded random search it leads by +0.20 pp at 2 evaluations, is tied by 5, and is behind by 12 (-0.37 pp). Without the seed, classical search ties the advisor by 12 evaluations and beats it by 40 (+0.6 to +0.8 pp, p <= 1e-4). Two LLM-specific behaviors survive: a single-task exploration failure (vehicle), and a rule-based confidence filter that removes ~33% of wasted compute without changing accuracy. The recommendation is deflationary: on tabular HPO, seed classical search with a sensible default; an LLM advisor adds no measurable generalization benefit and is overtaken within a handful of evaluations. We release the harness and a script that reproduces every statistic.

Related papers

• Your Retriever Already Knows: Distribution-Shape QPP for RAG Retrieval Sufficiency [0.0]
  Motivated by a Czech nuclear-regulator deployment, we compare three Query Performance Prediction (QPP) paradigms for retrieval sufficiency in RAG.<n>Our 24 non-lexical features reach a weighted-average AUROC of 0.856 at 2 ms per query, ahead of a classic-QPP literature pool.<n>Adding the LLM judgment as one feature (hybrid) matches S1 on ViDoRe (0.863) but gains a statistically significant edge on SJB.
  arXiv  Detail & Related papers  (2026-09-10T14:52:16Z)
• Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems [72.27018654934386]
  Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences.<n>In recommender systems, however, user feedback is rarely pairwise.<n>We propose Mult-DPO, a tractable multinomial surrogate likelihood over set-wise preference events for the user-preference alignment of LLM-based recommender systems.
  arXiv  Detail & Related papers  (2026-06-08T18:53:45Z)
• Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection [0.0]
  Multi-agent debate improves factuality and reasoning, but most recipes pick a fixed round count.<n>We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute governor for LLM debates.<n>On GSM8K the rule stops in 1.01 average rounds (4.06 LLM calls) at 97.0% accuracy vs 99.0% for fixed-5 debate at 15 calls: a 3.7x call reduction at -2pp accuracy.<n>On MMLU the calibrated KL collapses to about 0 and the rule caps on 99.5% of items at 2.1x cost.
  arXiv  Detail & Related papers  (2026-05-18T23:43:12Z)
• Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers [0.0]
  Large language models (LLMs) typically approach optimization as an inference-time procedure, solving each instance separately.<n>We study this question on Synergistic Dependency Selection (SDS), a controlled variant of constrained Quadratic Knapsack.<n>We fine-tune Qwen2.5-Coder-14B-Instruct with Group Relative Policy Optimization using a feasibility-gated reward and light structural scaffolding.
  arXiv  Detail & Related papers  (2026-05-18T13:21:40Z)
• Greedy Is a Strong Default: Agents as Iterative Optimizers [0.22843885788439797]
  We replace the random proposal generator with an LLM agent that reasons about evaluation diagnostics to propose informed candidates.<n>We evaluate on four tasks spanning discrete, mixed, and continuous search spaces.
  arXiv  Detail & Related papers  (2026-03-28T21:26:40Z)
• Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch [42.242102214102566]
  We show that an LLM agent that edits training source code in an unconstrained search space narrows the gap to classical methods.<n>We introduce Centaur, a hybrid that shares CMA-ES's internal state, including mean vector, step-size, and covariance matrix.<n> Centaur achieves the best result in our experiments, with its 0.8B variant outperforming the 27B variant.
  arXiv  Detail & Related papers  (2026-03-25T17:29:40Z)
• OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling [62.19438812624467]
  Large language models (LLMs) have exhibited their problem-solving abilities in mathematical reasoning.<n>We propose OptiBench, a benchmark for End-to-end optimization problem-solving with human-readable inputs and outputs.
  arXiv  Detail & Related papers  (2024-07-13T13:27:57Z)
• How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments [83.78240828340681]
  GAMA($gamma$)-Bench is a new framework for evaluating Large Language Models' Gaming Ability in Multi-Agent environments.<n>$gamma$-Bench includes eight classical game theory scenarios and a dynamic scoring scheme specially designed to assess LLMs' performance.<n>Our results indicate GPT-3.5 demonstrates strong robustness but limited generalizability, which can be enhanced using methods like Chain-of-Thought.
  arXiv  Detail & Related papers  (2024-03-18T14:04:47Z)
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models [66.12432440863816]
  We propose Prometheus, a fully open-source Large Language Model (LLM) that is on par with GPT-4's evaluation capabilities. Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics. Prometheus achieves the highest accuracy on two human preference benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:50:08Z)
• Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization [101.08992036691673]
  This paper explores a realistic unsupervised fine-tuning scenario, considering the presence of out-of-distribution samples from unknown classes. In particular, we focus on simultaneously enhancing out-of-distribution detection and the recognition of instances associated with known classes. We present a simple, efficient, and effective approach called Universal Entropy Optimization (UEO)
  arXiv  Detail & Related papers  (2023-08-24T16:47:17Z)
• Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting [65.00288634420812]
  Pairwise Ranking Prompting (PRP) is a technique to significantly reduce the burden on Large Language Models (LLMs) Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs.
  arXiv  Detail & Related papers  (2023-06-30T11:32:25Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.